Supply Chain Labs

Service unavailable

Turning tracking data
into operator decisions

Detention fees and missed appointments are operational failures created by estimates teams cannot trust. This demo turns ETA, dwell, and lane context into decision support an operator can act on.

Quick-Start Scenarios

Click any scenario to auto-fill the form with a realistic context.

Peak-hour Chicago → LA
Morning rush departure, Friday
Overnight LA → Chicago
Late-night departure, off-peak
Same-day Chicago → Dallas
Midday Tuesday departure
1,745 mi · 48h avg

How It Works

1
Lane lookup
Lambda reads lane_averages.csv from Object store scv-data-curated on cold start, caches in-memory.
2
ETA calculation
Adds avg_transit_hours to depart_time and returns predicted_eta as ISO 8601 timestamp.
3
Access control layer
x-api-key header validated against SHA-256 hash stored in scv-keys-store Object store bucket.

Service model

Service layerServerless workflow endpoint
Operating dataLane baseline dataset
Access controlScoped demo key
Prediction methodLane-average baseline
Supply Chain Labs · Live service demoView source on GitHub →